Can Codestral 22B v0.1 run on Mac mini M4 64GB?

YES — Runs Great

C46Usable

▲Estimated — low-sample bucket· few comparable runs

Codestral 22B v0.1 needs ~23.8 GB VRAM. Mac mini M4 64GB has 46.1 GB. With Q4_K_M quantization, expect ~9 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 23.8 GB, 9.0 tok/s, Runs well

23.8 GB required46.1 GB available

52% VRAM used

Fit status

Runs well

Decode

9.0 tok/s

TTFT

21479 ms

Safe context

154K

Memory

23.8 GB / 46.1 GB

Memory breakdown

Weights13.4 GB

KV Cache2.6 GB

Runtime0.9 GB

Headroom6.9 GB

See how fast it feels

See how fast it feelsCodestral 22B v0.1 on Mac mini M4 64GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
 """Sort a list using the quicksort algorithm.

 Args:
 arr: List of integers to sort.

 Returns:
 A new sorted list.
 """
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 9.0 tok/s decode · 21.5s TTFT (warm) · 23 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	9.0 tok/s	11716 ms	154K
Coding	C	Runs well	9.0 tok/s	21479 ms	154K
Agentic Coding	C	Runs well	9.0 tok/s	31242 ms	154K
Reasoning	C	Runs well	9.0 tok/s	25384 ms	154K
RAG	C	Runs well	9.0 tok/s	39053 ms	154K

Quantization options

How Codestral 22B v0.1 (22B params) fits at each quantization level on Mac mini M4 64GB (46.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	C43
Q3_K_S	3	10.8 GB	Low	C43
NVFP4	4	12.3 GB	Medium	C44
Q4_K_M	4	13.4 GB	Medium	C44
Q5_K_M	5	15.8 GB	High	C45
Q6_K	6	18.0 GB	High	C46
Q8_0Best for your GPU	8	23.5 GB	Very High	C48
F16	16	45.1 GB	Maximum	F0